REAL-TIME MONITORING OF ENVIRONMENTAL INFORMATION AND MODELING OF THE PHOTOSYNTHETIC RATE OF TOMATO PLANTS UNDER GREENHOUSE CONDITIONS

Horticultural research has shown that the yield and guano, of tomato crops are increased with the application of the appropriate amount of carbon dioxide (CO2). In this study, a wireless sensor network system was developed to monitor greenhouse environmental parameters in real time, including air temperature, humidity, CO2 concentration, soil temperature, soil moisture, and light intensity. An LI-6400XT portable photosynthesis analyzer was used to measure the photosynthetic rate of tomato plants. Prediction models of the photosynthetic rate of single leaves were established based on the back-propagation neural network. The relationship between CO2 concentration and photosynthetic rate was analyzed based on the models. Three stages of tomato growth were monitored, early seedling stage, late seedling stage, and flowering stage. Mean impact value (MIV) analysis was used in determining the relative importance of each input and in filtering the variables that had minimal effects to reduce the variables of input and make the models more accurate. The results showed that CO2 was not an important factor in the early seedling stage but significantly affected the photosynthetic rate in the other two stages. The prediction results of the models showed that the correlation coefficient between the simulated and observed data sets was higher than 0.99. On the other hand, when dfferent CO2 concentrations were selected as the input of the models to predict the photosynthetic rate, the simulated and observed data exhibited the same trend as long as the other environmental information remained unchanged. As the CO2 concentration in the atmosphere is lower than that required by tomato plants for growth, the models described herein would be useful in CO2 fertilization under greenhouse conditions.